Triple
T23263995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Franks |
E582093
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object |
Crossfire
Crossfire is a jazz-fusion band best known for collaborating and touring with American singer-songwriter Michael Franks.
|
E1576490
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Crossfire | Statement: [Michael Franks, associatedAct, Crossfire]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crossfire Context triple: [Michael Franks, associatedAct, Crossfire]
-
A.
Crossfire
Crossfire is a 1947 American film noir crime drama noted for its bold treatment of anti-Semitism and its ensemble cast, including Gloria Grahame.
-
B.
Crossfire
Crossfire was a long-running CNN political debate television program known for its combative left-right commentary format.
-
C.
Crossfire
Crossfire is a British thriller drama television series following a holiday resort under siege, starring Keeley Hawes.
-
D.
Crossfire
Crossfire is a notable work created by the AI research and art collective Gaia, recognized for exploring the intersection of artificial intelligence, creativity, and interactive digital media.
-
E.
Crossfire
"Crossfire" is a blues-rock song by Stevie Ray Vaughan and Double Trouble, known for its driving groove, punchy horn section, and socially conscious lyrics.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Crossfire Triple: [Michael Franks, associatedAct, Crossfire]
Generated description
Crossfire is a jazz-fusion band best known for collaborating and touring with American singer-songwriter Michael Franks.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Crossfire Target entity description: Crossfire is a jazz-fusion band best known for collaborating and touring with American singer-songwriter Michael Franks.
-
A.
Crossfire
"Crossfire" is a blues-rock song by Stevie Ray Vaughan and Double Trouble, known for its driving groove, punchy horn section, and socially conscious lyrics.
-
B.
Crossfire
Crossfire is a high-energy song by the South Korean boy group Stray Kids, known for its intense production and powerful choreography.
-
C.
Crossfire
Crossfire is a notable work created by the AI research and art collective Gaia, recognized for exploring the intersection of artificial intelligence, creativity, and interactive digital media.
-
D.
Crossfire
Crossfire is a 1947 American film noir crime drama noted for its bold treatment of anti-Semitism and its ensemble cast, including Gloria Grahame.
-
E.
Crossfire
Crossfire was a long-running CNN political debate television program known for its combative left-right commentary format.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e246079f58819085eaa9c260906880 |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f194cb76c48190869915cd93b44fcc |
completed | April 29, 2026, 5:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c3f723d4081909c2ff75ba4ada497 |
completed | May 19, 2026, 10:46 a.m. |
| NEDg | Description generation | batch_6a0c405be1188190b6622665e448bbe7 |
completed | May 19, 2026, 10:50 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c40bece448190bb9fd1a3058a1f06 |
completed | May 19, 2026, 10:51 a.m. |
Created at: April 17, 2026, 4:11 p.m.